Centralized power prediction method and system for multi-field station
By establishing an environment and power consumption database in multiple electric fields, calculating errors and establishing prediction models, the problems of high switching costs and large errors of traditional power prediction systems are solved, and the centralized prediction and accuracy improvement of multiple stations are achieved.
Patent Information
- Application Number
- PCT/CN2024/093881
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-05-17
- Publication Date
- 2024-11-28
AI Technical Summary
The traditional power prediction system is deployed on the site side, and the switching enterprise has high service costs and long cycles, and the prediction error is relatively obvious, which affects the accuracy of the prediction results.
Using the centralized power prediction method of multi-field stations, the environmental coefficient database and power consumption standard database are established to calculate the errors between the actual power data and the predicted power data, and the predicted power model is established. The various electric fields are calculated by combining the meteorological prediction data and date thresholds. and add them to obtain the centralized power prediction data of multiple stations.
It realizes seamless switching of data sources, reduces cost investment in service replacement, saves equipment procurement and maintenance costs, and improves prediction accuracy.
Smart Images

Figure CN2024093881_28112024_PF_FP_ABST
Abstract
Description
A method and system for predicting centralized power of multiple stations Technical Field
[0001] The present invention relates to the technical field of power prediction, and more particularly to a centralized power prediction method and system for multiple stations. Background Art
[0002] As power market reforms deepen, power generation companies increasingly need to participate in power market ancillary services in a targeted and accurate manner. Traditional power forecasting systems are deployed at the power station side, and power forecast data is reported by the power station side. Only one company's equipment and systems can be used in a power station within a cycle. The service cost of switching companies is high and the cycle is long. The system can only be upgraded on-site, and the service upgrade and optimization cost is high and the cycle is long. In addition, in the traditional power forecasting process, errors are relatively obvious and have a great impact on the accuracy of the forecast results.
[0003] Summary of the Invention
[0004] In order to solve the above problems, the present invention provides the following technical solutions:
[0005] A centralized power prediction method for multiple stations, comprising:
[0006] Step 1: Establish a corresponding environmental coefficient database and power consumption standard database for each electric field;
[0007] Step 2: Establish corresponding actual power database and predicted power database for each electric field;
[0008] Step 3: Calculate the error between the actual power data and the predicted power data;
[0009] Step 4: Establish a power prediction model, input the environmental coefficient, power consumption standard and error of each electric field prediction day into the power prediction model, and calculate the predicted power data of each electric field;
[0010] Step 5: Add the predicted power data of each electric field to obtain the centralized power prediction data of multiple stations.
[0011] Preferably, in the above-mentioned method for centralized power prediction of multiple sites, the step of establishing a corresponding environmental coefficient database and a power consumption standard database for each electric field includes:
[0012] Step 1: Install an environmental monitoring device and a power consumption monitoring device on each electric field side;
[0013] Step 2: storing the historical power consumption data acquired by the power consumption monitoring device in the power consumption standard database corresponding to the electric field; the power consumption standard database stores the power consumption data for each day in the past year;
[0014] Step 3: Calculate the relationship between the power consumption of each electric field and the environmental state under different environments in the historical data, generate an environmental coefficient, and save the environmental coefficient and its corresponding environmental state into the environmental coefficient database of the corresponding electric field;
[0015] Step 4: Generate environmental thresholds based on the environmental status in the environmental coefficient database, each environmental threshold corresponds to its environmental coefficient; generate date thresholds based on the dates in the electricity consumption standard database, each date threshold corresponds to its electricity consumption data for that day.
[0016] Preferably, in the above-mentioned method for centralized power prediction of multiple stations, the establishing of an actual power database and a predicted power database corresponding to each electric field includes:
[0017] Step 1: Install a power monitoring device on each side of the electric field to detect the actual power of the electric field every day;
[0018] Step 2: Obtain the historical actual power and historical predicted power of each electric field, and insert date tags into the historical actual power and historical predicted power respectively;
[0019] Step three: classify the historical actual power and the historical predicted power carrying the tags according to their date tags and store them in the actual power database and the predicted power database of the respective electric fields.
[0020] Preferably, in the above-mentioned method for centralized power prediction of multiple stations, the calculating of the error between the actual power data and the predicted power data includes:
[0021] Step 1: selecting historical actual power data and historical predicted power data within a limited period from the actual power database and the predicted power database of each electric field respectively;
[0022] Step 2: Calculate the difference between the predicted power data and the actual power data for the same electric field and the same date label;
[0023] Step 3: Add the above differences and divide them by the number of items selected according to the limited period to obtain the average error of each electric field.
[0024] Preferably, in the above-mentioned method for centralized power prediction of multiple stations, establishing a prediction power model, respectively bringing the environmental coefficient, power consumption standard, and error of each electric field prediction day into the prediction power model, and calculating the prediction power data of each electric field includes:
[0025] Step 1: Establish the predicted power model
[0026] Among them, P Tis the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A is the power consumption standard of the electric field on the predicted day, t is 24 hours, J N is the average error of the electric field on the predicted day;
[0027] Step 2: Compare the meteorological forecast data of each electric field on the forecast day with the environmental threshold in the environmental coefficient database, and obtain the corresponding environmental coefficient I according to the matching environmental threshold. A , and substitute it into the model;
[0028] Step 3: Compare the date of the predicted day with the date threshold in the electricity standard database, and obtain the corresponding electricity consumption standard W according to the matching date threshold. A , and substitute it into the model;
[0029] Step 4: Calculate the average error J based on the error model N1 ;
[0030] The error model is
[0031] Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the forecast date, Q T-N To predict the actual power data N days before the date, N is the number of items selected according to the limited period;
[0032] Substituting the predicted power data and the actual power data corresponding to the actual power database and the predicted power database of the corresponding electric field into the error model respectively, and calculating the average error of the predicted power of the electric field;
[0033] Step 5: Substitute the average error of the electric field into the predicted power model to obtain the predicted power data of the electric field on the predicted day.
[0034] Preferably, in the above-mentioned method for predicting the centralized power of multiple stations, the step of adding the predicted power data of each electric field to obtain the centralized power prediction data of multiple stations includes:
[0035] Step 1: Use the predicted power model Calculate the predicted power data of the remaining electric fields on the forecast day, which are P T1 、P T2 、P T3 …P TM ;
[0036] Step 2: PT1 、P T2 、P T3 …P TM The data are stored in the predicted power database of each electric field according to the corresponding date;
[0037] Step 3: Calculate the centralized power prediction data P of multiple stations T0 =P T1 +P T2 +P T3 +…+P TM .
[0038] A centralized power prediction system for multiple stations, comprising:
[0039] A detection module is provided on the electric field side and is used to obtain basic data of each electric field;
[0040] A storage module, connected to the detection module, for organizing and storing the detected basic data;
[0041] A calculation integration module is connected to the integrated storage module, and calculates the predicted power data of each electric field on the prediction day through the preset predicted power model; and generates multi-station centralized power prediction data based on the predicted power data of each electric field on the prediction day.
[0042] Preferably, in the above-mentioned multi-station centralized power prediction system, the detection module includes:
[0043] A weather forecast unit is provided with a plurality of corresponding electric fields, each for predicting weather forecast information of the corresponding electric field; a plurality of environmental detection units are provided with a plurality of corresponding electric fields, each for detecting the environmental status of the corresponding electric field within a day;
[0044] There are multiple power consumption detection units corresponding to the number of electric fields, each used to detect the power consumption data of each electric field within a day; there are multiple actual power detection units corresponding to the number of electric fields, each used to detect the actual power data of each electric field within a day.
[0045] Preferably, in the above-mentioned multi-station centralized power prediction system, the storage module includes:
[0046] The power consumption standard database is connected to the power consumption detection unit and is used to store the power consumption data of each electric field and generate a date threshold according to the detection date of the power consumption data;
[0047] The environmental coefficient database is connected to the environmental detection unit and is used to store the environmental status of each electric field and generate a corresponding environmental coefficient based on the environmental status of the day and the power consumption data of the day. The environmental coefficient represents the coefficient of change of power consumption under the environmental status. The environmental coefficient database generates environmental thresholds based on the environmental status, and each environmental threshold corresponds to its environmental coefficient.
[0048] The actual power database is connected to the actual power detection unit and is used to store the power data actually used by each electric field every day;
[0049] The predicted power database is connected to the calculation integration module and is used to store the power data predicted to be used by each electric field every day.
[0050] Preferably, in the above-mentioned multi-station centralized power prediction system, the calculation integration module includes:
[0051] The predictive power model, Among them, P T is the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A is the power consumption standard of the electric field on the predicted day, t is 24 hours, J N is the average error of the electric field on the predicted day;
[0052] The error model, Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the forecast date, Q T-N To predict the actual power data N days before the date, N is the number of items selected according to the limited period;
[0053] The substitution module is connected to the power consumption standard database, the environmental coefficient database, the actual power database, the predicted power database, the predicted power model and the error model, and is used to substitute the corresponding data in the above databases into the above models to obtain the predicted power data P of each electric field on the predicted day. T1 、P T2 、P T3 …P TM , and the predicted power data is stored in the predicted power database of each electric field;
[0054] Prediction of multi-station centralized power model, P T0 =P T1 +P T2 +P T3 +…+PTM ;
[0055] Substitute the above data into the multi-station centralized power prediction model to obtain the multi-station centralized power prediction data P T0 .
[0056] It can be seen from the above technical solutions that compared with the prior art, the present application has the following beneficial effects:
[0057] 1. The present invention realizes centralized prediction and centralized reporting, realizes seamless switching of data sources, and avoids the cost investment caused by replacing power prediction services;
[0058] 2. When building a new power station, the present invention only requires configuring the station environment and power calculation device, and does not require configuring power prediction equipment and systems, which can save equipment procurement, maintenance and subsequent upgrade costs;
[0059] 3. The present invention improves the accuracy of prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0061] FIG1 is a flow chart of the method of the present invention;
[0062] FIG2 is a flow chart of the system of the present invention. DETAILED DESCRIPTION
[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0064] In the present invention, the terms "first", "second" and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise clearly defined. Terms such as "installed", "connected", "connected", and "fixed" should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In the description of the present invention, it should be understood that the directions or positional relationships indicated by the terms "upper", "lower", "left", "right", "front", and "rear" are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or unit referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.
[0065] Throughout this specification, terms such as "one embodiment," "some embodiments," and "specific embodiments" mean that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
[0066] Example 1
[0067] In one embodiment, referring to FIG1 , a method for centralized power prediction of multiple stations includes:
[0068] Step 1: Establish a corresponding environmental coefficient database and power consumption standard database for each electric field;
[0069] Step 2: Establish corresponding actual power database and predicted power database for each electric field;
[0070] Step 3: Calculate the error between the actual power data and the predicted power data;
[0071] Step 4: Establish a power prediction model, input the environmental coefficient, power consumption standard, and error of each electric field prediction day into the power prediction model, and calculate the predicted power data of each electric field;
[0072] Step 5: Add the predicted power data of each electric field to obtain the centralized power prediction data of multiple stations.
[0073] The principle of the above embodiment is: by independently setting up a database in each electric field, obtaining the predicted power data of each electric field through the prediction model, and then obtaining the centralized prediction effect of multiple stations after integration.
[0074] The beneficial effects of the above embodiment are: breaking the original single and fixed power prediction service model of the site, realizing centralized prediction and centralized reporting, realizing seamless switching of data sources, and avoiding the cost investment caused by replacing power prediction services.
[0075] Example 2
[0076] In one embodiment, referring to FIG1 , a method for centralized power prediction of multiple stations is shown, S1 including:
[0077] S11, an environmental monitoring device and a power consumption monitoring device are installed on each side of the electric field;
[0078] S12, storing the historical power consumption data acquired by the power consumption monitoring device in a power consumption standard database corresponding to the electric field; the power consumption standard database stores the power consumption data for each day in the past year;
[0079] S13, calculating the relationship between the power consumption of each electric field and the environmental state under different environments in the historical data, generating an environmental coefficient, and saving the environmental coefficient and its corresponding environmental state in an environmental coefficient database of the corresponding electric field;
[0080] S14, generating environmental thresholds based on the environmental conditions in the environmental coefficient database, each environmental threshold corresponding to its environmental coefficient; generating date thresholds based on the dates in the electricity consumption standard database, each date threshold corresponding to its electricity consumption data for that day;
[0081] S2 includes:
[0082] S21, a power monitoring device is installed on each side of the electric field to detect the actual power of the electric field every day;
[0083] S22, obtaining the historical actual power and the historical predicted power of each electric field, and inserting date tags into the historical actual power and the historical predicted power respectively;
[0084] S23, classifying the historical actual power and the historical predicted power with the tags according to their date tags and storing them in the actual power database and the predicted power database of the respective electric fields;
[0085] S3 includes:
[0086] S31, respectively selecting historical actual power data and historical predicted power data within a limited period from the actual power database and predicted power database of each electric field;
[0087] S32, respectively calculating the difference between the predicted power data and the actual power data for the same electric field and the same date tag;
[0088] S33, adding the above differences and dividing by the number of items selected according to the limited period to obtain the average error of each electric field;
[0089] S4 includes:
[0090] S41, establish a prediction power model
[0091] Among them, P T is the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A is the power consumption standard of the electric field on the predicted day, t is 24 hours, J N is the average error of the electric field on the predicted day;
[0092] S42, comparing the meteorological forecast data of each electric field on the forecast day with the environmental threshold in the environmental coefficient database, and obtaining the corresponding environmental coefficient I according to the matching environmental threshold. A and substitute it into the model; wherein the weather forecast data is preferably provided by the weather forecast;
[0093] S43, compare the date of the predicted day with the date threshold in the electricity standard database, and obtain the corresponding electricity consumption standard W according to the matched date threshold. A , and substitute it into the model;
[0094] S44, calculate the average error J according to the error model N1 ;
[0095] The error model is
[0096] Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the forecast date, Q T-N To predict the actual power data N days before the date, N is the number of items selected according to the limited period;
[0097] Substitute the predicted power data and actual power data corresponding to the actual power database and the predicted power database of the corresponding electric field into the error model respectively, and calculate the average error of the predicted power of the electric field;
[0098] S45, substituting the average error of the electric field into a predicted power model to obtain predicted power data for the electric field prediction day;
[0099] S5 includes:
[0100] S51, through the prediction power model Calculate the predicted power data of the remaining electric fields on the forecast day, which are P T1 、P T2 、P T3 …P TM ;
[0101] S52, P T1 、P T2 、P T3 …P TM The data are stored in the predicted power database of each electric field according to the corresponding date;
[0102] S53, calculate the multi-station centralized power prediction data P T0 =P T1 +P T2 +P T3 +…+P TM .
[0103] The beneficial effects of the above embodiment are: by establishing the relationship between the environment and electricity consumption, and the electricity consumption of each day in the past year corresponds to the electricity consumption of each day this year, the electricity consumption on holidays and weekdays is distinguished according to date, thereby increasing the accuracy of the prediction; through the difference between historical predictions and actual conditions, an error average is generated, and the error average is then brought into the calculation model as an error, which can ensure that the prediction gradually becomes stable and accurate; and a newly built electric field only needs to be equipped with an environmental monitor, a weather forecast device and a power recording device at the site, and no power prediction device is required, which can save equipment procurement, maintenance and subsequent upgrade costs.
[0104] Example 3
[0105] In one embodiment, referring to FIG2 , a centralized power prediction system for multiple stations includes:
[0106] A detection module is provided on the electric field side and is used to obtain basic data of each electric field;
[0107] A storage module, connected to the detection module, for organizing and storing the detected basic data;
[0108] A calculation integration module is connected to the integration storage module, and calculates the predicted power data of each electric field on the prediction day through a preset prediction power model; and generates multi-station centralized power prediction data based on the predicted power data of each electric field on the prediction day; wherein the detection module includes: a weather forecast unit, which is provided with a plurality of corresponding electric fields, and is respectively used to predict the weather forecast information of the corresponding electric field; an environment detection unit, which is provided with a plurality of corresponding electric fields, and is respectively used to detect the environmental status of the respective electric field within a day; a power consumption detection unit, which is provided with a plurality of corresponding electric fields, and is respectively used to detect the power consumption data of the respective electric field within a day; an actual power detection unit, which is provided with a plurality of corresponding electric fields, and is respectively used to detect the actual power data of the respective electric field within a day;
[0109] The storage module includes: a power consumption standard database, which is connected to the power consumption detection unit and is used to store the power consumption data of each electric field and generate a date threshold based on the detection date of the power consumption data; an environmental coefficient database, which is connected to the environmental detection unit and is used to store the environmental status of each electric field and generate a corresponding environmental coefficient based on the environmental status of the day and the power consumption data of the day, and the environmental coefficient represents the coefficient of change of power consumption under the environmental status; the environmental coefficient database generates environmental thresholds based on the environmental status, and each environmental threshold corresponds to its environmental coefficient; an actual power database, which is connected to the actual power detection unit and is used to store the power data actually used by each electric field every day; a predicted power database, which is connected to the calculation integration module and is used to store the power data predicted to be used by each electric field every day;
[0110] The calculation integration module includes: prediction power model, Among them, P T is the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A is the power consumption standard of the electric field on the predicted day, t is 24 hours, J N is the average error of the electric field on the predicted day; error model, Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the forecast date, Q T-N To predict the actual power data of N days before the day, N is the number of items selected according to the limited period; the substitution module is connected with the power consumption standard database, environmental coefficient database, actual power database, predicted power database, predicted power model and error model, and is used to substitute the corresponding data in the above database into the above model to obtain the predicted power data P of each electric field on the prediction day. T1 、P T2 、PT3 …P TM , and the predicted power data is stored in the predicted power database of each electric field; predict the centralized power model of multiple stations, P T0 =P T1 +P T2 +P T3 +…+P TM ; Substitute the above data into the prediction model of multiple station centralized power to obtain the centralized power prediction data P of multiple stations T0 .
[0111] The beneficial effects of the above embodiment are: organically integrating the detection, storage modules and calculation, realizing prediction integration, forming a closed-loop prediction and detection system, improving prediction accuracy while increasing prediction speed.
[0112] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps and are not to be regarded as improper limitations of the present invention.
[0113] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, method, article, or apparatus.
[0114] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.
[0115] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations as fall within the scope of the claims and their equivalents, and to enable those skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for predicting centralized power of multiple stations, characterized in that: include: Step 1: Establish a corresponding environmental coefficient database and power consumption standard database for each electric field; Step 2: Establishing corresponding actual power database and predicted power database for each electric field; Step 3, calculating the error between the actual power data and the predicted power data; Step 4: Establish a prediction power model, bring the environmental coefficient, power consumption standard and error of each electric field prediction day into the prediction power model, and calculate the prediction power data of each electric field; Step 5: Add the predicted power data of each electric field to obtain the concentrated power prediction data of multiple stations.
2. A method for predicting concentrated power of multiple stations according to claim 1, characterized in that: The establishment of a corresponding environmental coefficient database and a power consumption standard database for each electric field includes: Step 1: Install an environmental monitoring device and a power consumption monitoring device on each electric field side; Step 2: storing the historical power consumption data acquired by the power consumption monitoring device in the power consumption standard database of the corresponding electric field; the power consumption standard database stores the power consumption data of each day in the past year; Step 3, calculating the relationship between the power consumption of each electric field and the environmental state under different environments in the historical data, generating an environmental coefficient, and saving the environmental coefficient and its corresponding environmental state into the environmental coefficient database of the corresponding electric field; Step 4: Generate environmental thresholds based on the environmental conditions in the environmental coefficient database. The environmental threshold corresponds to its environmental coefficient; the date threshold is generated according to the date in the electricity consumption standard database, and each date threshold corresponds to the electricity consumption data of the day.
3. A method for predicting concentrated power of multiple stations according to claim 2, characterized in that: The establishment of an actual power database and a predicted power database corresponding to each electric field includes: Step 1: Install a power monitoring device on each electric field side to detect the actual power of the electric field every day; Step 2: Obtain the historical actual power and historical predicted power of each electric field, and insert date tags into the historical actual power and historical predicted power respectively; Step three, classify the historical actual power and the historical predicted power carrying the tags according to their date tags and store them in the actual power database and the predicted power database of the respective electric fields.
4. A method for predicting concentrated power of multiple stations according to claim 3, characterized in that: The calculation of the error between the actual power data and the predicted power data includes: Step 1, respectively selecting historical actual power data and historical predicted power data within a limited period from the actual power database and the predicted power database of each electric field; Step 2, respectively calculating the difference between the predicted power data and the actual power data of the same electric field and the same date label; Step three, add the above differences and divide them by the number of items selected according to the limited period to obtain the average error of each electric field.
5. A method for predicting concentrated power of multiple stations according to claim 4, characterized in that: The power prediction model is established, and the environmental coefficient, power consumption standard and error of each electric field prediction day are respectively introduced into the power prediction model to calculate the predicted power data of each electric field, including: Step 1: Establish the predicted power model Among them, P T is the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A is the power consumption standard of the electric field on the predicted day, t is 24 hours, J N is the average error of the electric field on the predicted day; Step 2: Compare the meteorological forecast data of each electric field on the forecast day with the environmental threshold in the environmental coefficient database, and obtain the corresponding environmental coefficient I according to the matched environmental threshold. A , and substitute it into the model; Step 3: Compare the date of the predicted day with the date threshold in the electricity standard database, and obtain the corresponding electricity consumption standard W according to the matched date threshold. A , and substitute it into the model; Step 4: Calculate the average error J according to the error model N1 ; The error model is Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the prediction date, Q T-N To predict the actual power data N days before the day, N is the number of items selected according to the limited period; Substituting the predicted power data and the actual power data corresponding to the actual power database and the predicted power database of the corresponding electric field into the error model respectively, and calculating the average error of the predicted power of the electric field; Step 5: Substitute the average error of the electric field into the predicted power model to obtain the predicted power data of the electric field on the predicted day.
6. A method for predicting concentrated power of multiple stations according to claim 5, characterized in that: The step of adding the predicted power data of each electric field to obtain the concentrated power prediction data of multiple stations includes: Step 1: Using the predicted power model Calculate the predicted power data of the remaining electric fields on the prediction day, which are P T1 , P T2 , P T3 …P TM ; Step 2: P T1 , P T2 , P T3 …P TM The predicted power databases of the respective electric fields are stored according to the corresponding dates; Step 3: Calculate the centralized power prediction data P of multiple stations T0 =P T1 +P T2 +P T3 +…+P TM .
7. A centralized power prediction system for multiple stations, based on a centralized power prediction method for multiple stations provided in claims 1-6, characterized in that: include: A detection module, which is arranged on the electric field side and is used to obtain basic data of each electric field; A storage module, connected to the detection module, for organizing and storing the detected basic data; A calculation integration module is connected to the integration storage module, and calculates the predicted power data of each electric field on the prediction day through the preset predicted power model; and generates multi-station centralized power prediction data based on the predicted power data of each electric field on the prediction day.
8. A centralized power prediction system for multiple stations according to claim 7, characterized in that: The detection module comprises: A weather forecast unit, which has a plurality of corresponding electric fields and is used to predict weather forecast information of the corresponding electric fields respectively; The environmental detection unit has multiple corresponding electric field units, each of which is used to detect the electric field Environmental conditions during the day; A power consumption detection unit is provided with a plurality of units corresponding to the number of electric fields, each of which is used to detect the power consumption data of each electric field within one day; The actual power detection unit is provided in plurality corresponding to the number of electric fields, and is used to detect the actual power data of the respective electric fields within one day.
9. A centralized power prediction system for multiple stations according to claim 8, characterized in that: The storage module comprises: The power consumption standard database is connected to the power consumption detection unit and is used to store the power consumption data of each electric field and generate a date threshold value according to the detection date of the power consumption data; the environmental coefficient database is connected to the environmental detection unit and is used to store the environmental state of each electric field and generate a corresponding environmental coefficient according to the environmental state of the day and the power consumption data of the day, and the environmental coefficient represents the coefficient of change of the power consumption under the environmental state; the environmental coefficient database generates an environmental threshold value according to the environmental state, and each environmental threshold value corresponds to its environmental coefficient; The actual power database is connected to the actual power detection unit and is used to store the power data actually used by each electric field every day; The predicted power database is connected to the calculation integration module and is used to store the power data predicted to be used by each electric field every day.
10. A centralized power prediction system for multiple stations according to claim 9, characterized in that: The computing integration module includes: The predictive power model, Among them, P T is the predicted power data of the electric field on the predicted day, I A is the environmental coefficient of the electric field on the predicted day, W A To predict the electric field Electricity standard, t is 24 hours, J N is the average error of the electric field on the predicted day; The error model, Among them, P T-1 is the predicted power data for the day before the forecast, Q T-1 To predict the actual power data of the day before, P T-N The predicted power data N days before the prediction date, Q T-N To predict the actual power data N days before the day, N is the number of items selected according to the limited period; The substitution module is connected to the power consumption standard database, the environmental coefficient database, the actual power database, the predicted power database, the predicted power model and the error model, and is used to substitute the corresponding data in the above database into the above model to obtain the predicted power data P of each electric field on the predicted day. T1 , P T2 , P T3 …P TM , and the predicted power data is correspondingly stored in the predicted power database of each electric field; Prediction of multi-station centralized power model, P T0 =P T1 +P T2 +P T3 +…+P TM ; Substitute the above data into the multi-station centralized power prediction model to obtain the centralized power prediction data P of multiple stations T0 .
Citation Information
Patent Citations
Regional power grid new energy generation power prediction optimization method and device
CN110705771A
Regional power grid wind power generation power prediction optimization method and device
CN110705772A
Power grid load prediction method, device and system under new energy grid-connected condition
CN111582544A
Concentrated power prediction method and system for multiple stations
CN116780504A
Method and system for predicting a day-ahead wind power of wind farms
US20230136352A1
